Search Results for "token" - Page 11
Sort By:
Showing 616 open source projects for "token"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Error to trace to log to deploy. One click. No SSH.AppSignal links every error to the trace, the trace to the log, the log to the deploy that shipped it.
-
1
OpenClaw Office
OpenClaw Office is the visual monitoring and management frontend
...The platform enables real-time visualization of agent states, interactions, and workflows, making complex multi-agent coordination easier to understand and debug. Users can observe communication flows between agents through visual connections, track token usage and operational costs, and analyze performance through integrated dashboards and charts. The system also includes live chat capabilities, allowing users to monitor conversations and tool calls as they occur. -
2
Code2Prompt
Convert codebases into structured prompts optimized for LLM analysis
code2prompt is an open source command line tool designed to convert an entire codebase into a structured prompt that can be easily used with large language models. It analyzes a project directory, gathers relevant source files, and formats them into a single prompt that includes the source tree and code content. This approach helps developers quickly provide full project context to AI models without manually copying files or assembling prompts. code2prompt is built in Rust and focuses on... -
3
AutoTrain Advanced
Faster and easier training and deployments
...The project provides a no-code and low-code interface that allows users to train models using custom datasets without needing extensive expertise in machine learning engineering. It supports a wide range of tasks including text classification, sequence-to-sequence modeling, token classification, sentence embedding training, and large language model fine-tuning. The system integrates closely with the Hugging Face ecosystem and allows developers to train models using datasets hosted on the Hugging Face Hub. AutoTrain Advanced can run locally or in cloud environments, making it adaptable to different computational setups. ... -
4
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
KVCache-Factory is an open-source research framework designed to explore and implement unified key-value cache compression techniques for autoregressive transformer models. In large language models, the key-value cache stores intermediate attention states that enable efficient token generation during inference, but these caches can consume large amounts of GPU memory when handling long contexts. KVCache-Factory provides a platform for implementing and evaluating multiple compression strategies that reduce memory usage while preserving model performance. The framework integrates several state-of-the-art methods such as PyramidKV, SnapKV, H2O, and StreamingLLM, allowing researchers to compare and experiment with different approaches within the same environment. ... -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
FastDeploy
High-performance Inference and Deployment Toolkit for LLMs and VLMs
...The platform enables developers to deploy trained models quickly using optimized inference pipelines that support GPUs, specialized AI accelerators, and other hardware architectures. FastDeploy includes advanced acceleration technologies such as speculative decoding, multi-token prediction, and efficient KV cache management to improve throughput and latency during inference. It also offers compatibility with OpenAI-style APIs and vLLM-like interfaces, allowing developers to integrate deployed models easily into existing applications and services. -
6
Nano-vLLM
A lightweight vLLM implementation built from scratch
Nano-vLLM is a lightweight implementation of the vLLM inference engine designed to run large language models efficiently while maintaining a minimal and readable codebase. The project recreates the core functionality of vLLM in a simplified architecture written in approximately a thousand lines of Python, making it easier for developers and researchers to understand how modern LLM inference systems work. Despite its compact design, nano-vllm incorporates advanced optimization techniques such... -
7
SafeClaw
Chat with it via text and voice
...It emphasizes privacy and predictability by using traditional programming, rule-based intent parsing, and established machine learning tools rather than large language models, meaning there are no per-token API costs and deterministic behavior. The assistant offers features such as voice control using fully local speech-to-text (Whisper) and text-to-speech (Piper) capabilities, news aggregation with extractive summarization, and smart home or Bluetooth device control. SafeClaw supports multiple channels, including CLI and Telegram, and avoids prompt injection risk because it doesn’t rely on LLMs for core operations. -
8
Ling-V2
Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI
Ling-V2 is an open-source family of Mixture-of-Experts (MoE) large language models developed by the InclusionAI research organization with the goal of combining state-of-the-art performance, efficiency, and openness for next-generation AI applications. It introduces highly sparse architectures where only a fraction of the model’s parameters are activated per input token, enabling models like Ling-mini-2.0 to achieve reasoning and instruction-following capabilities on par with much larger dense models while remaining significantly more computationally efficient. Trained on more than 20 trillion tokens of high-quality data and enhanced through multi-stage supervised fine-tuning and reinforcement learning, Ling-V2’s models demonstrate strong general reasoning, mathematical problem-solving, coding understanding, and knowledge-intensive task performance. -
9
LLM TLDR
95% token savings. 155x faster queries. 16 languages
LLM TLDR is a tool that leverages large language models (LLMs) to generate concise, coherent summaries (TL;DRs) of long documents, articles, or text files, helping users quickly understand large amounts of content without reading every word. It integrates with LLM APIs to handle input texts of varying lengths and complexity, applying techniques like chunking, context management, and multi-pass summarization to preserve accuracy even when the source is very large. The system supports both... -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
Step3-VL-10B
Multimodal model achieving SOTA performance
...Despite having only about 10 billion parameters, it delivers performance that rivals or even surpasses much larger models (10×–20× larger) on a wide range of multimodal benchmarks covering reasoning, perception, and complex tasks, positioning it as one of the most powerful models in its class. It achieves this efficiency and strong performance through unified pre-training on a massive 1.2 trillion-token multimodal corpus that jointly optimizes a language-aligned perception encoder with a powerful decoder, creating deep synergy between image processing and text understanding. -
11
Chinese-XLNet
Chinese XLNet pre-trained model
...Unlike traditional masked language modeling, XLNet uses a permutation language modeling objective that captures bidirectional context more effectively by training over all possible token orderings, yielding richer contextual representations. This model is trained on large-scale Chinese text datasets to learn linguistic patterns, long-range dependencies, and semantic nuance typical of Chinese writing, making it useful for tasks like text classification, question answering, named entity recognition, and language generation. ... -
12
3FS
A high-performance distributed file system
The 3FS repository (standing likely for “Feature 3F System” or similar) is focused on providing a feature extraction and transformation framework tailored to deep and large models, especially in token-based systems. Its primary aim is to support efficient and scalable feature transformation pipelines—especially for inference environments—by batching, caching, and integrating feature-based modules like segmenters, sparse retrievers, and scorers seamlessly. The repo includes APIs to define components (e.g. seg, ret, scor) that wrap or interface with external or internal modules, as well as logic to schedule and compose these feature transforms. ... -
13
OpenAuth
Universal, standards-based auth provider
...The project is designed to be infrastructure-friendly, aligning with managed stores and serverless platforms so sessions, webhooks, and callbacks work reliably at scale. It emphasizes secure defaults, including robust token handling, CSRF protections, and clear session lifecycles, while leaving room for customization where apps need it. Developers can bring their own database or storage layer and wire it through adapters without rewriting core logic. The goal is to remove boilerplate around sign-up/sign-in, user profiles, and authorization checks so teams can ship features faster. -
14
Resty
Simple HTTP and REST client library for Go
...Backoff Retry Mechanism with retry condition function reference. Resty client HTTP & REST Request and Response middleware. Request.SetContext supported. Authorization option of BasicAuth and Bearer token. Set request ContentLength value for all request or particular request. Custom Root Certificates and Client Certificates. Download/Save HTTP response directly into File, like curl -o flag. See SetOutputDirectory & SetOutput. Cookies for your request and CookieJar support. SRV Record based request instead of Host URL. Client settings like Timeout, RedirectPolicy, Proxy, TLSClientConfig, Transport, etc. ... -
15
Octokit
Ruby toolkit for the GitHub API
...While most methods return a Resource object or a Boolean, sometimes you may need access to the raw HTTP response headers. Access tokens can be revoked, removing access for only that token without having to change your password everywhere. Access tokens have access scopes that allow for more granular access to API resources. For instance, you can grant a third party access to your gists but not your private repositories. Two-Factor Authentication brings added security to the account by requiring more information to login. -
16
Bolt for JavaScript
A framework to build Slack apps using JavaScript
A JavaScript framework to build Slack apps in a flash with the latest platform features. Read the getting started guide to set-up and run your first Bolt app. To listen to messages that your app has access to receive, you can use the message() method which filters out events that aren’t of type message. message() accepts an optional pattern parameter of type string or RegExp object which filters out any messages that don’t match the pattern. A RegExp pattern can be used instead of a string... -
17
Nimiq Blockchain
JavaScript implementation of the Nimiq protocol
...A simple, secure and censorship-resistant payment protocol, native to the web. Nimiq is a decentralized, censorship-resistant payment protocol native to the web, with its own diverse ecosystem of apps. The native NIM token is transacted within Nimiq as a store and transfer of value: it acts as digital cash. The cutting-edge, browser-first blockchain approach means that users directly connect to the blockchain with nothing more than a browser. Therefore anyone with an up-to-date browser can join the payment network directly, pay and accept payments without having to install software or rely on unnecessary intermediaries. ... -
18
Apache Dubbo-go
Go Implementation For Apache Dubbo
Apache Dubbo-go, a Dubbo implementation written in Golang, is born to bridge the gap between Java/Dubbo and Go/X. Dubbo-go has supported many RPC protocols, like Triple, Dubbo JSONRPC, gRPC, HTTP, HTTP2. Triple is the supported protocol of Dubbo3 ecology and is a gRPC extended protocol based on HTTP2, which is compatible with the gRPC service. In other words, on the basis of gRPC's reliable invocation, it adds Dubbo's service governance capability. Dubbo protocol is traditional Dubbo ecology... -
19
rest.js
GitHub REST API client for JavaScript
GitHub REST API client for JavaScript. Import the Octokit constructor based on your platform. Instantiate your octokit API. All options are optional, but authentication is strongly encouraged. API Previews can be enabled globally by setting the previews option. They can be set per-request as well. A default time zone can be enabled by setting the timeZone option. In order to use Octokit with GitHub Enterprise, set the baseUrl option. Most of GitHub’s REST API endpoints have matching methods.... -
20
PHP OAuth 2.0 Server
A spec compliant, secure by default
...In order to prevent man-in-the-middle attacks, the authorization server MUST require the use of TLS with server authentication as defined by RFC2818 for any request sent to the authorization and token endpoints. The client MUST validate the authorization server’s TLS certificate as defined by RFC6125. -
21
MiniMax-M2.5
State of the art LLM and coding model
...The model supports full-stack development across web, mobile, and desktop platforms, covering the entire lifecycle from system design to testing and code review. With native serving speeds of up to 100 tokens per second, it completes complex agentic tasks significantly faster than previous versions while maintaining high token efficiency. M2.5 is built to be highly cost-effective, enabling continuous deployment of powerful AI agents at a fraction of the cost of other frontier models. -
22
Coinbase Agentic Wallet Skills
npx skills add coinbase/agentic-wallet-skills
Coinbase Agentic Wallet Skills project is a modular skill library developed by Coinbase as part of its Agentic Wallet ecosystem, designed to give AI agents direct access to on-chain financial operations through a standardized and reusable interface. It provides a set of pre-built “skills” that abstract complex blockchain interactions into simple, callable capabilities, allowing agents to authenticate, manage funds, and execute transactions without requiring developers to implement low-level... -
23
NVIDIA NeMo Agent Toolkit
Library for efficiently connecting and optimizing teams of AI agents
...The toolkit integrates with popular agent frameworks such as LangChain, LlamaIndex, CrewAI, Microsoft Semantic Kernel, and Google ADK. Developers can monitor agent execution, trace workflows, and analyze token-level performance to identify bottlenecks and improve efficiency. NeMo Agent Toolkit also supports evaluation systems, prompt optimization, and reinforcement learning techniques to enhance agent behavior over time. By combining instrumentation, workflow orchestration, and performance optimization tools, the platform helps developers deploy scalable and intelligent multi-agent systems. -
24
OpenClaw Opik Observability Plugin
Official plugin for OpenClaw that exports agent traces to Opik
...Each time an AI agent performs an action—such as calling a large language model, invoking a tool, accessing memory, or delegating to a sub-agent—the plugin records the full interaction and sends it to Opik for analysis and visualization. This allows developers to inspect inputs, outputs, token usage, latency, and execution flow across complex multi-step agent workflows. The goal of the project is to provide transparency into the internal reasoning and operational pipeline of agent systems so developers can diagnose failures, control costs, and improve reliability. -
25
xsrfprobe
Advanced toolkit for detecting and exploiting CSRF vulnerabilities
XSRFProbe is an advanced security auditing toolkit designed to detect and analyze Cross Site Request Forgery (CSRF/XSRF) vulnerabilities in web applications. It uses an automated crawling engine that continuously scans a target application, collects forms and endpoints, and evaluates them for potential CSRF weaknesses. XSRFProbe performs numerous systematic checks to determine whether a web endpoint is vulnerable, including inspection of anti-CSRF tokens, cookie validation behavior, and...
